Two-Dimensional Quantitative Profifiling of Cell Morphology with Serous Effusion by Unsupervised Machine Learning Analysis

Abstract

Cytological evaluation of serous effusion specimens is an important part of cancer diagnosis. In thisstudy we performed two-dimensional (2D) morphometric features and clustering analysis fordevelopment of useful techniques for identification and differentiation of malignant and begin cells inserous effusion specimens extracted from ten patients with clinical symptoms of pleural and peritonealeffusion. Our findings show that the two-dimensional (2D) morphometric features and clustering analysisare useful techniques for identification and differentiation of malignant and begin cells in serous effusionspecimens, which can lead to development of new methods for rapid cells profiling in clinical application.